{ "openapi": "3.0.1", "info": { "title": "DataCite Scraper (Datasets, Software, Research Outputs)", "description": "Search DataCite, the CC0 DOI registry for research outputs beyond journal articles -- 133M+ datasets, software, samples, instruments, images, text, workflows and dissertations. Lucene query plus filters (type, publisher, year, provider, ORCID, ROR, funding). Cursor pagination past 10k. DOI lookup.", "version": "0.1", "x-build-id": "9RfD0acuTlrqxgtHb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapyx~datacite-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapyx-datacite-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapyx~datacite-scraper/runs": { "post": { "operationId": "runs-sync-scrapyx-datacite-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapyx~datacite-scraper/run-sync": { "post": { "operationId": "run-sync-scrapyx-datacite-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "mode": { "title": "Mode", "enum": [ "search", "dois" ], "type": "string", "description": "`search` runs a query / filters against the DataCite index (133M+ DOIs). `dois` looks up specific DOIs.", "default": "search" }, "query": { "title": "Search query", "type": "string", "description": "`search` mode. Lucene syntax against titles / descriptions / creators / subjects, e.g. `climate model`, `\"sea surface temperature\"`, `creators.name:Smith`. Optional if you supply filters instead." }, "dois": { "title": "DOIs", "type": "array", "description": "`dois` mode. One per line: `10.5281/zenodo.1234567`, a `https://doi.org/...` URL, or `doi:...`. A DOI that DataCite did not register (e.g. a Crossref journal DOI) becomes a `record_not_found` error.", "items": { "type": "string" } }, "resourceType": { "title": "Resource type", "type": "string", "description": "`search` filter. One DataCite type: `dataset`, `software`, `text`, `image`, `physical-object`, `audiovisual`, `collection`, `conference-paper`, `dissertation`, `preprint`, `report`, `workflow`, `computational-notebook`, `model`, `instrument`, `other`. An unknown value would return zero results silently, so it is rejected." }, "publisher": { "title": "Publisher / repository", "type": "string", "description": "`search` filter. e.g. `Zenodo`, `Dryad`, `PANGAEA`, `figshare`, `Harvard Dataverse`." }, "fromPublicationYear": { "title": "From publication year", "type": "integer", "description": "`search` filter. Keep DOIs published in or after this year." }, "toPublicationYear": { "title": "To publication year", "type": "integer", "description": "`search` filter. Keep DOIs published in or before this year." }, "createdYear": { "title": "Created year", "type": "integer", "description": "`search` filter. Year the DOI metadata was first created at DataCite." }, "registeredYear": { "title": "Registered year", "type": "integer", "description": "`search` filter. Year the DOI was registered (findable)." }, "providerId": { "title": "Provider ID", "type": "string", "description": "`search` filter. A DataCite member (consortium) id, e.g. `cern`, `bl` (British Library), `tib`." }, "clientId": { "title": "Client / repository ID", "type": "string", "description": "`search` filter. A specific repository id, e.g. `cern.zenodo`, `dryad.dryad`, `pangaea.repository`." }, "prefix": { "title": "DOI prefix", "type": "string", "description": "`search` filter. A DOI prefix, e.g. `10.5281` (Zenodo), `10.5061` (Dryad)." }, "personId": { "title": "Person ID (ORCID)", "type": "string", "description": "`search` filter. An ORCID (`0000-0001-2345-6789` or the full URL) — DOIs with this person as a creator or contributor." }, "affiliationId": { "title": "Affiliation ID (ROR)", "type": "string", "description": "`search` filter. A ROR id — DOIs with a creator affiliated to this organisation." }, "subject": { "title": "Subject", "type": "string", "description": "`search` filter. A subject / keyword phrase, matched against `subjects.subject`." }, "hasCitations": { "title": "Has citations", "type": "boolean", "description": "`search` filter. Keep only DOIs with at least one recorded citation.", "default": false }, "hasViews": { "title": "Has views", "type": "boolean", "description": "`search` filter. Keep only DOIs with at least one recorded view.", "default": false }, "hasDownloads": { "title": "Has downloads", "type": "boolean", "description": "`search` filter. Keep only DOIs with at least one recorded download.", "default": false }, "hasFunding": { "title": "Has funding", "type": "boolean", "description": "`search` filter. Keep only DOIs with a funding reference.", "default": false }, "rawQuery": { "title": "Raw query (power users)", "type": "string", "description": "Appended verbatim (AND-joined) to the composed `query`. Full Elasticsearch query-string syntax, e.g. `types.resourceType:\"Specimen\"`, `container.title:*`." }, "slimOutput": { "title": "Slim output (drop raw)", "type": "boolean", "description": "By default every RESULT row carries the verbatim DataCite record in `raw`. Turn on for the normalised fields only.", "default": false }, "maxResults": { "title": "Max results", "minimum": 1, "type": "integer", "description": "`search` mode cap. Cursor pagination is used, so this can exceed 10,000.", "default": 500 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Parallel in-flight requests (matters for `dois` mode).", "default": 4 }, "minRequestInterval": { "title": "Min seconds between requests", "minimum": 0, "type": "number", "description": "Politeness pacing for a non-profit's infrastructure.", "default": 0.3 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. No anti-bot layer, so a proxy is OFF by default.", "default": { "useApifyProxy": false } } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }